© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 197003
    Prev
    Next
    INDEX
    Explanations

    code and punctuation

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     J
    0.47
    الج
    0.46
     الج
    0.45
     аб
    0.45
     سود
    0.43
    جراء
    0.41
     SUD
    0.41
    اب
    0.40
     س
    0.38
     företag
    0.38
    POSITIVE LOGITS
     Mas
    0.54
     Sand
    0.50
    sand
    0.46
    Sand
    0.46
    Mas
    0.45
     mas
    0.45
    mas
    0.44
     Cont
    0.43
     cont
    0.43
    砾
    0.43
    Activations Density 0.000%

    No Known Activations